Study on Feature Extraction of Handwritten Chinese Character Using Gabor Filters

摘要：

On the issue of feature extraction of handwritten Chinese characters, this study presents a method: first of all, normalize the width of the strokes, and then obtain the Chinese characteristics using the Gabor transform based on the elastic-grid. Experiments show that this method has higher noise rejection, compared with the pure Grid characteristics or Gabor transform characteristics. Chinese character recognition accuracy also has been greatly improved.

关键词： Gabor Filter Elastic Meshing Off-line handwritten Chinese characters normalize stroke width

作者: Shaohui Zhang Xiangnian Huang Xiang Pan

作者单位: School of Mathematics and Computer Engineering, Xihua University, Chengdu, China

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 234-236

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）